Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 6149
    Prev
    Next
    INDEX
    Explanations

    words related to the term "rot"

    oai_token-act-pair · gpt-3.5-turbo

    specific references to "rot" in various contexts, likely related to decay or deterioration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    natureconservancy
    -0.78
    BILITIES
    -0.68
    ãģŁ
    -0.64
    externalActionCode
    -0.64
     pronounced
    -0.62
    isSpecialOrderable
    -0.62
    lished
    -0.60
    lyss
    -0.60
     sudden
    -0.60
    ihilation
    -0.58
    POSITIVE LOGITS
    rot
    1.30
    Rot
    0.91
    omy
    0.90
    chet
    0.88
    ate
    0.86
    unda
    0.83
    oscope
    0.83
    ection
    0.81
    ected
    0.80
    warm
    0.80
    Activations Density 0.006%

    No Known Activations